Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011210422> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3011210422 endingPage "800" @default.
- W3011210422 startingPage "793" @default.
- W3011210422 abstract "Though the domain of big data and artificial intelligence in health care continues to evolve, there is a lack of systemic methods to improve data quality and streamline the preparation process. To address this, we aimed to develop an automated sorting system (RetiSort) that accurately labels the type and laterality of retinal photographs. Cross-sectional study. RetiSort was developed with retinal photographs from the Singapore Epidemiology of Eye Diseases (SEED) study. The development of RetiSort was composed of 3 steps: 2 deep-learning (DL) algorithms and 1 rule-based classifier. For step 1, a DL algorithm was developed to locate the optic disc, the “landmark feature.” For step 2, based on the location of the optic disc derived from step 1, a rule-based classifier was developed to sort retinal photographs into 3 types: macular-centered, optic disc–centered, or related to other fields. Step 2 concurrently distinguished laterality (i.e., the left or right eye) of macular-centered photographs. For step 3, an additional DL algorithm was developed to differentiate the laterality of disc-centered photographs. Via the 3 steps, RetiSort sorted and labeled retinal images into (1) right macular–centered, (2) left macular–centered, (3) right optic disc–centered, (4) left optic disc–centered, and (5) images relating to other fields. Subsequently, the accuracy of RetiSort was evaluated on 5000 randomly selected retinal images from SEED as well as on 3 publicly available image databases (DIARETDB0, HEI-MED, and Drishti-GS). The main outcome measure was the accuracy for sorting of retinal photographs. RetiSort mislabeled 48 out of 5000 retinal images from SEED, representing an overall accuracy of 99.0% (95% confidence interval [CI], 98.7–99.3). In external tests, RetiSort mislabeled 1, 0, and 2 images, respectively, from DIARETDB0, HEI-MED, and Drishti-GS, representing an accuracy of 99.2% (95% CI, 95.8–99.9), 100%, and 98.0% (95% CI, 93.1–99.8), respectively. Saliency maps consistently showed that the DL algorithm in step 3 required pixels in the central left lateral border and optic disc of optic disc–centered retinal photographs to differentiate the laterality. RetiSort is a highly accurate automated sorting system. It can aid in data preparation and has practical applications in DL research that uses retinal photographs." @default.
- W3011210422 created "2020-03-23" @default.
- W3011210422 creator A5001410583 @default.
- W3011210422 creator A5008184108 @default.
- W3011210422 creator A5012909562 @default.
- W3011210422 creator A5020727354 @default.
- W3011210422 creator A5032625133 @default.
- W3011210422 creator A5032933669 @default.
- W3011210422 creator A5038442711 @default.
- W3011210422 creator A5042798102 @default.
- W3011210422 creator A5068357228 @default.
- W3011210422 creator A5072258594 @default.
- W3011210422 date "2020-08-01" @default.
- W3011210422 modified "2023-10-03" @default.
- W3011210422 title "Deep Learning for Automated Sorting of Retinal Photographs" @default.
- W3011210422 cites W1994266547 @default.
- W3011210422 cites W1995023030 @default.
- W3011210422 cites W2752747624 @default.
- W3011210422 cites W2758333670 @default.
- W3011210422 cites W2772246530 @default.
- W3011210422 cites W2792026451 @default.
- W3011210422 cites W2796809202 @default.
- W3011210422 cites W2800012666 @default.
- W3011210422 cites W2886801379 @default.
- W3011210422 cites W2891146096 @default.
- W3011210422 cites W2898192966 @default.
- W3011210422 cites W2935464137 @default.
- W3011210422 cites W2942760134 @default.
- W3011210422 cites W2950848962 @default.
- W3011210422 cites W3151556911 @default.
- W3011210422 doi "https://doi.org/10.1016/j.oret.2020.03.007" @default.
- W3011210422 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32362553" @default.
- W3011210422 hasPublicationYear "2020" @default.
- W3011210422 type Work @default.
- W3011210422 sameAs 3011210422 @default.
- W3011210422 citedByCount "12" @default.
- W3011210422 countsByYear W30112104222020 @default.
- W3011210422 countsByYear W30112104222021 @default.
- W3011210422 countsByYear W30112104222022 @default.
- W3011210422 countsByYear W30112104222023 @default.
- W3011210422 crossrefType "journal-article" @default.
- W3011210422 hasAuthorship W3011210422A5001410583 @default.
- W3011210422 hasAuthorship W3011210422A5008184108 @default.
- W3011210422 hasAuthorship W3011210422A5012909562 @default.
- W3011210422 hasAuthorship W3011210422A5020727354 @default.
- W3011210422 hasAuthorship W3011210422A5032625133 @default.
- W3011210422 hasAuthorship W3011210422A5032933669 @default.
- W3011210422 hasAuthorship W3011210422A5038442711 @default.
- W3011210422 hasAuthorship W3011210422A5042798102 @default.
- W3011210422 hasAuthorship W3011210422A5068357228 @default.
- W3011210422 hasAuthorship W3011210422A5072258594 @default.
- W3011210422 hasConcept C118487528 @default.
- W3011210422 hasConcept C119767625 @default.
- W3011210422 hasConcept C154945302 @default.
- W3011210422 hasConcept C171508891 @default.
- W3011210422 hasConcept C2779735895 @default.
- W3011210422 hasConcept C2780827179 @default.
- W3011210422 hasConcept C31972630 @default.
- W3011210422 hasConcept C41008148 @default.
- W3011210422 hasConcept C548259974 @default.
- W3011210422 hasConcept C71924100 @default.
- W3011210422 hasConcept C95623464 @default.
- W3011210422 hasConceptScore W3011210422C118487528 @default.
- W3011210422 hasConceptScore W3011210422C119767625 @default.
- W3011210422 hasConceptScore W3011210422C154945302 @default.
- W3011210422 hasConceptScore W3011210422C171508891 @default.
- W3011210422 hasConceptScore W3011210422C2779735895 @default.
- W3011210422 hasConceptScore W3011210422C2780827179 @default.
- W3011210422 hasConceptScore W3011210422C31972630 @default.
- W3011210422 hasConceptScore W3011210422C41008148 @default.
- W3011210422 hasConceptScore W3011210422C548259974 @default.
- W3011210422 hasConceptScore W3011210422C71924100 @default.
- W3011210422 hasConceptScore W3011210422C95623464 @default.
- W3011210422 hasFunder F4320334737 @default.
- W3011210422 hasIssue "8" @default.
- W3011210422 hasLocation W30112104221 @default.
- W3011210422 hasOpenAccess W3011210422 @default.
- W3011210422 hasPrimaryLocation W30112104221 @default.
- W3011210422 hasRelatedWork W1974070334 @default.
- W3011210422 hasRelatedWork W1989642498 @default.
- W3011210422 hasRelatedWork W1996742056 @default.
- W3011210422 hasRelatedWork W2006801159 @default.
- W3011210422 hasRelatedWork W2374377624 @default.
- W3011210422 hasRelatedWork W2501264958 @default.
- W3011210422 hasRelatedWork W2529858135 @default.
- W3011210422 hasRelatedWork W3206904435 @default.
- W3011210422 hasRelatedWork W4290099501 @default.
- W3011210422 hasRelatedWork W576871667 @default.
- W3011210422 hasVolume "4" @default.
- W3011210422 isParatext "false" @default.
- W3011210422 isRetracted "false" @default.
- W3011210422 magId "3011210422" @default.
- W3011210422 workType "article" @default.